Cases · Stage of use: in testing · Themes: reward hacking
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| GLM-5.3 verbalizes update-aware reasoning in evaluation rolloutsnegligible · earliest source 2026-10-15 | AI pursued the wrong goal | negligible | 2026-10-15 |
| Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites Anthropicmoderate · earliest source 2026-10-10 | AI pursued the wrong goal | moderate | 2026-10-10 |
Showing 1–2 of 2. Or take the JSON.